MACGAN: An All-in-One Image Restoration under Adverse Conditions Using Multidomain Attention-Based Conditional GAN

Abstract

Various vision-based tasks suffer from inaccurate navigation and poor performance due to inevitable problems, such as adverse weather conditions like haze, fog, rain, snow, and clouds affecting ground and aerial navigation, as well as underwater images being degraded with blue-green tones and mud affecting marine navigation. Existing techniques in the literature typically focus on restoring specific degradations using separate models, leading to computational inefficiency. To address this, an all-in-one Multidomain Attention-based Conditional Generative Adversarial Network (MACGAN) is proposed to improve scene visibility for optimal ground, aerial, and marine navigation, using the same set of parameters across all domains. The MACGAN is a lightweight network with four encoder and decoder blocks and multiple attention blocks in between, which enhances the image restoration process by focusing on the most important features. To evaluate the effectiveness of MACGAN, extensive qualitative and quantitative comparisons are conducted with state-of-the-art image-to-image translation models, all-in-one adverse weather removal models, and single-effect removal models. The results highlight the superior performance of MACGAN in terms of scene visibility improvement and restoration quality. Additionally, MACGAN is tested on real-world unseen image domains, including smog, dust, fog, rain, snow, and lightning, further validating its generalizability and robustness. Furthermore, an ablation study is conducted to analyze the contributions of the discriminator and attention blocks within the MACGAN architecture. The results confirm that both components play significant roles in the effectiveness of MACGAN, with the discriminator ensuring adversarial training and the attention blocks effectively capturing and enhancing important image features.